From 78b93072d6f16bfece06713ab2d4e18213af1e28 Mon Sep 17 00:00:00 2001 From: zack Zhiyuan Li Date: Thu, 21 Nov 2024 06:21:53 +0000 Subject: [PATCH 1/2] update version --- nexa/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nexa/__init__.py b/nexa/__init__.py index b53e36d3..c2582443 100644 --- a/nexa/__init__.py +++ b/nexa/__init__.py @@ -1 +1 @@ -__version__ = "0.0.9.2" +__version__ = "0.0.9.3" From 456d14aa345ce99d61442af8810f04af5518f8d1 Mon Sep 17 00:00:00 2001 From: zack Zhiyuan Li Date: Thu, 21 Nov 2024 06:23:45 +0000 Subject: [PATCH 2/2] update README --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index eb427b93..5cd436f9 100644 --- a/README.md +++ b/README.md @@ -20,9 +20,9 @@ - **Local UI:** Streamlit for interactive model deployment and testing ## Latest News 🔥 - -- Support Nexa AI's own vision language model (0.9B parameters): `nexa run omnivision` and audio language model (2.9B): `nexa run omniaudio` +- Support Nexa AI's own vision language model (0.9B parameters): `nexa run omnivision` and audio language model (2.9B parameters): `nexa run omniaudio` - Support audio language model: `nexa run qwen2audio`, **we are the first open-source toolkit to support audio language model with GGML tensor library.** +- Support iOS Swift binding for local inference on **iOS mobile** devices. - Support embedding model: `nexa embed ` - Support pull and run supported Computer Vision models in GGUF format from HuggingFace or ModelScope: `nexa run -hf -mt COMPUTER_VISION` or `nexa run -ms -mt COMPUTER_VISION` - Support pull and run NLP models in GGUF format from HuggingFace or ModelScope: `nexa run -hf -mt NLP` or `nexa run -ms -mt NLP`